Max Robotics — Global Service Robot Directory + US Certification

About

Alex LaGrassa is a roboticist whose research lies at the intersection of task planning, lifelong learning, and robotic manipulation. His work tackles a fundamental challenge in robotics: enabling robots to autonomously acquire new skills and solve novel tasks over extended deployments without manual reprogramming. LaGrassa’s most influential contribution is his development of search-based task planning frameworks that leverage learned skill effect models. By predicting the outcomes of actions, these models allow robots to compose skills flexibly—even when those skills have complex, interdependent effects—eliminating the need for rigid, task-specific plan skeletons. His work on hierarchical object-centric controllers further advances this vision, showing how manipulation tasks can be decomposed into parallel subtasks controlled relative to the objects themselves. With over 28 citations across his key papers, LaGrassa’s research is gaining traction for its practical approach to lifelong robotic autonomy. Notably, his 2022 paper on learning model preconditions for planning with multiple models addresses the critical trade-off between analytical models (fast but narrow) and physics simulators (accurate but slow), paving the way for more efficient, adaptable robot planners.